基于随机梯度法的选择性神经网络二次集成

Two-level Ensembles of Selective Neural Network Based on Stochastic Gradient

针对使用贪心法、遗传算法等方法实现选择性神经网络集成时出现的“局部最小点”和“过拟合”问题,提出了一类基于随机梯度法的选择性神经网络二次集成方法。理论分析和实验表明,与上述选择性神经网络集成方法相比,该方法易于实现且效果明显。

In the application of greedy method or genetic algorithm for the selection of the components of neural network ensembles, local minima and over fitting problems occur frequently. To solve such problems, a kind of method of two-level stochastic gradient-based selective neural network ensembles is proposed in this paper. Theoretical analyses and experimental results show that the method is easy to be constructed and performs well.